Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12103
    Prev
    Next
    INDEX
    Explanations

    math simplification and evaluation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _resource
    -0.08
    .resource
    -0.07
     newcomer
    -0.07
    bu
    -0.07
    *Math
    -0.07
     Resource
    -0.07
    。这
    -0.07
    Community
    -0.07
    اردة
    -0.07
    Resource
    -0.07
    POSITIVE LOGITS
     eerst
    0.09
     dahulu
    0.08
     cancellations
    0.08
     chimi
    0.08
     sobie
    0.08
     teatr
    0.08
     cancellation
    0.08
    red
    0.08
     dulu
    0.07
     Akt
    0.07
    Activations Density 0.013%

    No Known Activations